A Machine Learning Framework for Predicting and Understanding the Canadian Drought Monitor
Bibliographic record
Abstract
Abstract Drought is a costly natural disaster that impacts economies and ecosystems worldwide, so monitoring drought and communicating its impacts to individuals, communities, industry, and governments is important for mitigation, adaptation, and decision‐making. This research describes a novel machine learning framework to predict and understand the Canadian Drought Monitor (CDM). This fully automated approach is trained on nearly two decades of expert analysis and would assist the comprehensive monitoring of drought impacts without the continued requirement of ground support, a benefit in many data‐limited areas across the country. The framework also integrates the Shapley Additive Explanation (SHAP) variable importance metric to provide insight into drought dynamics in near real‐time, demonstrating its usefulness for understanding the value of different data sets for drought assessments and dispelling the commonly held misconception that machine learning models are not useful for inference. The results demonstrate that the model can effectively predict the CDM maps and realistically capture the evolution of drought events over time. A SHAP analysis found that the Prairie drought of 2015 was related to a strong El Niño event that reduced water supply to a region already facing long‐term water deficits, and the subsequent reduction in groundwater availability was detected by the Gravity Recovery and Climate Experiment satellite. Overall, this research shows strong potential to streamline the CDM methodology, integrate scientific insight into operations in near real‐time using SHAP values, and provide an avenue to retrospectively extend the CDM for evaluating current and future drought events in a historical context.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".